- Writing Code Since 2016
- Deep Learning & Tech Lover Since 2015
Main: Multi-Modal Understanding / Reasoning / Efficient AI
Side: Video Games / J-POP / Movie
MMRefine: Unveiling the Obstacles to Robust Refinement in Multimodal Large Language Models
Gio Paik, G. Kim and J. Im. ACL Findings 2025 (To appear)
Improving Fine-grained Visual Understanding in VLMs through Text-Only Training
D. Choi, G. Son, S. Kim, Gio Paik, S. Hong. AAAI Workshop 2025 (arxiv)
- ML Engineer at Theta One (2025.02.17. ~ )
- Research Intern at Vision Understanding Team, NAVER CLOUD (2024.07.15. ~ 2025.01.10.)
- Undergrad. Researcher at Sejong Robotics and Computer Vision Lab (2023.01.03. ~ 2024.04.05.)
- Software Specialist at ISMG, Republic of Korea Air Force (2021.03.15. ~ 2022.12.14.)